Skip to main content
Glama
deenesjakoruzh
SHAYOUWORLD

egov-law-mcp

by SHAYOUWORLD
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

@codeagentjp/egov-law-mcp

Локальный MCP-сервер (stdio) для поиска японских законов и получения текста статей из e-Gov Law Search.

Этот сервер не вызывает LLM. Он только возвращает данные о законах с указанием источника и URL-адреса e-Gov, чтобы ваш MCP-клиент (Claude Desktop, Claude Code, Cursor или любой другой агент) мог сослаться на первоисточник.

Выбор архитектурных решений был основан на изучении открытого исходного кода Lawsy-Custom-BQ от Агентства цифровых технологий (опубликован 24.04.2026 в рамках выпуска правительственного ИИ Gennai OSS). См. заметки о проектировании на codeagent.jp.

Зачем нужен еще один e-Gov MCP

На npm уже существует egov-law-mcp от другого автора. Этот пакет отличается тремя особенностями:

  1. find_related_laws — ищет указы об исполнении (施行令) и нормативные акты (施行規則) для заданного базового закона. В Lawsy-Custom-BQ реализован такой же шаг на стороне сервера; это полезно, так как определения и делегированные правила часто находятся вне основного закона.

  2. Указание источника в каждом результате инструмента — каждый ответ включает название закона, ID закона, номер статьи и канонический URL e-Gov, поэтому вызывающая LLM не сможет пропустить ссылку.

  3. Однофайловый .mjs, без этапа сборки — bin/egov-law-mcp.mjs запускается непосредственно в Node 20+. Легче проверять, меньше размер установки.

Related MCP server: Houki e-Gov MCP Server

Статус

MVP. API намеренно сделан минималистичным:

  • search_laws — поиск действующих японских законов по ключевым словам.

  • get_article — получение конкретной статьи закона по ID или номеру закона.

  • get_law — получение базовых метаданных и предварительного просмотра текста закона.

  • find_related_laws — поиск потенциально связанных указов об исполнении и нормативных актов.

Требования

  • Node.js 20 или новее

  • Сетевой доступ к https://laws.e-gov.go.jp

Установка

Из npm:

{
  "mcpServers": {
    "egov-law": {
      "command": "npx",
      "args": ["-y", "@codeagentjp/egov-law-mcp"]
    }
  }
}

Из исходного кода для разработки:

git clone https://github.com/SHAYOUWORLD/egov-law-mcp.git
cd egov-law-mcp
node bin/egov-law-mcp.mjs
{
  "mcpServers": {
    "egov-law": {
      "command": "node",
      "args": ["/absolute/path/to/egov-law-mcp/bin/egov-law-mcp.mjs"]
    }
  }
}

Инструменты

search_laws

Поиск в списке законов e-Gov.

{
  "keyword": "個人情報",
  "limit": 10
}

get_article

Получение текста статьи. Укажите lawId или lawNum.

{
  "lawId": "503AC0000000035",
  "article": "2"
}

get_law

Получение базовых метаданных и предварительного просмотра текста закона в формате простого текста.

{
  "lawId": "503AC0000000035",
  "previewChars": 3000
}

find_related_laws

Поиск законов, названия которых связаны с базовым законом, включая указы об исполнении и нормативные акты.

{
  "lawName": "個人情報の保護に関する法律",
  "limit": 10
}

Источник данных и атрибуция

Этот пакет использует API e-Gov Law Search:

Результаты инструментов включают указание источника. При публикации или распространении результатов, основанных на этом пакете, указывайте соответствующий источник e-Gov.

Рекомендуемая атрибуция:

出典: e-Gov法令検索（https://laws.e-gov.go.jp/）

Примечания по безопасности

  • Этот пакет является инструментом для поиска правовой информации, а не юридической консультацией. Проверяйте важные юридические выводы на официальной странице e-Gov и, при необходимости, консультируйтесь с квалифицированным специалистом.

  • Он не выполняет команды оболочки.

  • Он записывает сообщения JSON-RPC только в stdout, а логи — только в stderr.

  • Он обращается только к конечным точкам e-Gov Law Search.

Ссылки

Лицензия

MIT © codeagent.jp

Available Tools

4 tools
get_articleB

Retrieve a specific article from e-Gov Law Search by law ID or law number.

ParametersJSON Schema
NameRequiredDescriptionDefault
lawIdNoe-Gov law ID, for example 503AC0000000035.
lawNumNoJapanese law number. Either lawId or lawNum is required.
articleYesArticle number, for example 2.
paragraphNoOptional paragraph number.

TDQS

B3.3/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, and the description only states 'retrieve' without disclosing behavioral traits such as idempotency, authentication needs, rate limits, or error handling for missing articles.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that front-loads the core purpose. However, it may be too brief for a tool with four parameters, missing important details about parameter dependencies.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with four parameters and no output schema or annotations, the description omits crucial context: it does not mention that the 'article' parameter is required, nor does it explain what the return value contains or how errors are handled.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description's mention of 'by law ID or law number' adds minimal value beyond the existing schema descriptions, which already specify parameter purposes and constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the action (retrieve), resource (a specific article from e-Gov Law Search), and method (by law ID or law number). It distinguishes from sibling tools like get_law and search_laws by targeting articles specifically.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context (retrieving a specific article) but provides no explicit when-to-use or when-not-to-use guidance, nor does it reference alternatives among sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_lawA

Retrieve law metadata and a plain text preview from e-Gov Law Search.

ParametersJSON Schema
NameRequiredDescriptionDefault
lawIdNoe-Gov law ID. Either lawId or lawNum is required.
lawNumNoJapanese law number. Either lawId or lawNum is required.
previewCharsNoMaximum preview length. Defaults to 5000.

TDQS

A3.5/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided; description implies a read operation but doesn't explicitly confirm idempotency, authentication needs, or rate limits. It only states what is retrieved, which is adequate but not exhaustive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, clear, no unnecessary words. Front-loads the key action and resource.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 3 parameters, no output schema, and no annotations, the description is brief but covers the essential purpose. However, it lacks details about return format or side effects, which could be useful for a tool with no output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers 100% of parameters with descriptions. The description adds no extra meaning beyond the schema (e.g., 'metdata and preview' is generic). Baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it retrieves law metadata and plain text preview from e-Gov. It specifies the source and distinguishes from sibling tools like search_laws (search) and get_article (specific article).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus siblings, nor any prerequisites (e.g., need a law ID from search_laws). The description is silent on usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_lawsB

Search current Japanese laws from e-Gov Law Search by keyword.

ParametersJSON Schema
NameRequiredDescriptionDefault
keywordYesKeyword to search in law name, law number, or law ID.
categoryNoLaw category. Defaults to all.
limitNoMaximum number of results. Defaults to 10.

TDQS

B3.4/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description must disclose behavioral traits. It only mentions 'current' laws, but lacks details on authorization, rate limits, data freshness, or any side effects. The bare statement is insufficient for a search tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single concise sentence with no superfluous words. It front-loads the action and resource, perfect for quick comprehension.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and only three parameters, the description fails to explain return format, pagination, or result structure. Given the tool's complexity (search across categories), completeness is lacking.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description adds no extra meaning beyond the schema. The search logic (e.g., partial matching, case sensitivity) is not explained, meeting the baseline for high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'search', the resource 'current Japanese laws', and the source 'e-Gov Law Search by keyword', distinguishing it from siblings like find_related_laws and get_article which target specific relations or articles.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies general keyword search but does not explicitly state when to use this tool versus alternatives, nor does it mention when not to use it. No exclusions or prerequisites are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 4 tool updatesv0.1.0
    • First observedfind_related_laws
    • First observedget_article
    • First observedget_law
    • First observedsearch_laws
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.8/5.0

Scored across 4 tools

Disambiguation5/5

Each tool has a distinct purpose: searching laws, retrieving law metadata, retrieving specific articles, and finding related laws. No overlap in functionality.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case, e.g., search_laws, get_law, get_article, find_related_laws.

Tool Count5/5

With 4 tools, the server is well-scoped for a focused legal search assistant. The count is neither excessive nor insufficient.

Completeness4/5

The tool set covers the core operations for searching and retrieving Japanese laws and articles. A minor gap is the lack of a tool to list all laws, but for search purposes this is acceptable.

Maintenance

ActivityMaintained
ResponsivenessUnresponsive

Resources

Related MCP Connectors

Related MCP Servers